'How do I use keras's conv2D just to reduce the shape of input data?
I have a matrix of dimensions (611024). I want to use convolution and max-pooling operations to convert it into (L1024) dimensions. I don't want to train a model or anything but just need to perform this operation.
Precisely, I have a data frame of size (61*1024). I want to use layer1 over that dataframe and get the results after the operation.
layer1 = Conv2D(32, (3, 3), activation='relu', input_shape=(61, 1024, 1)
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|
